From December 7th to 9th, 2016, ACLR and the National Language Resource Monitoring and Research Plane Media Center, BLCU jointly organized the Language Resources Lecture Series. Prof. Zong Chengqing, Institute of Automation, Chinese Academy of Sciences, and Dr. Xue Nianwen, Associate Professor of computer science and linguistics program of Brandeis University were invited as the lecture guests to share research achievements with teachers and students around the construction of language resources.
Prof. Zong Chengqing delivered a lecture on the theme of Corpus Construction for Machine Translation. During the lecture, he introduced how to automatically or semi-automatically acquire large-scale and high-quality bilingual reference materials through the computer network, how to annotate bilingual reference materials for corpus-based machine translation system, and how to improve the translation quality of the translation engine with the help of the manually annotated corpus. Prof. Zong Chengqing also shared a framework of parallel bilingual resources acquisition and an automatic extraction method of parallel bilingual sentence segments, briefly analyzed the existing problems in current machine translation and put forward preliminary ideas for future research.
Prof. Xue Nianwen made two lectures entitled Towards a Universal Meaning Representation for Natural Language Processing and Scalability and Expressiveness in Discourse Annotation: Where is the Trade off? He introduced the semantic annotation projects of PropBank and CPB, and shared his experience in annotating discourse relations in Chinese text in the Penn Discourse TreeBank framework, as well as the experience in running the CoNLL Shared Task on Shallow Discourse Parsing in the last two years. Finally, he presented to the audience his work on annotating the discourse and dialogue structure of SMS message conversations.
